In recent years, deep learning techniques have made significant strides in molecular generation for specific targets, driving advancements in drug discovery. However, existing molecular generation methods present significant limitations: those operating at the atomic level often lack synthetic feasibility, drug-likeness, and interpretability, while fragment-based approaches frequently overlook comprehensive factors that influence protein-molecule interactions. To address these challenges, we propose a novel fragment-based molecular generation framework tailored for specific proteins. Our method begins by constructing a protein subpocket and molecular arm concept-based neural network, which systematically integrates interaction force information and geometric complementarity to sample molecular arms for specific protein subpockets. Subsequently, we introduce a diffusion model to generate molecular backbones that connect these arms, ensuring structural integrity and chemical diversity. Our approach significantly improves synthetic feasibility and binding affinity, with a 4% increase in drug-likeness and a 6% improvement in synthetic feasibility. Furthermore, by integrating explicit interaction data through a concept-based model, our framework enhances interpretability, offering valuable insights into the molecular design process.
View on arXiv@article{kuang2025_2503.08160,
title={ Concept-Driven Deep Learning for Enhanced Protein-Specific Molecular Generation },
author={ Taojie Kuang and Qianli Ma and Athanasios V. Vasilakos and Yu Wang and Qiang and Cheng and Zhixiang Ren },
journal={arXiv preprint arXiv:2503.08160},
year={ 2025 }
}